Deep learning segmentation of the cerebral ventricular system and brainstem for pediatric radiotherapy planning

Segmentation of the cerebral ventricular system (VS) is central to radiotherapy, both for whole-ventricular irradiation in intracranial germ cell tumors (GCTs) and protection of the periventricular region. Complex, variable VS anatomy makes manual delineation challenging and hampers auto-segmentation model development. We reported the evaluation and workflow integration of a deep-learning (DL) model for VS and brainstem segmentation on pediatric magnetic resonance imaging (MRI).

An nnU-Net was trained on MRIs from 76 unique brain tumor cases (n = 73/71 for T1/T2). The evaluation used two independent retrospective cohorts: (i) GCTs evaluated on planning computed tomography (CT) images after MRI-to-CT registration mapping (n = 13/14), and (ii) brain tumors evaluated on MRI (n = 14). Performance was assessed using the Dice similarity coefficient (DSC) and Hausdorff distances (HD) against manual contours. Prospective deployment in routine clinical planning assessed usability and workflow integration.

In the GCT-CT cohort, brainstem segmentations achieved median DSCs of >0.85 and HDs₉₅ of ≤5.0/6.4 mm, while VS segmentations achieved DSCs of >0.70 and HDs₉₅ of ≤5.3/4.3 mm, after rigid/deformable mapping to planning CT. In the MR cohort, performance on T1-/T2-weighted MRI reached DSCs of ≥0.90 for both structures, and HDs₉₅ of ≤3.0/3.4 mm and ≤ 1.3/2.2 mm for the brainstem and VS, respectively. The DL-segmentation workflow reduced workflow time by >50% compared with manual contouring.

Lower performance in the GCT-CT cohort likely reflects noisier CT-based references, interobserver variability, and uncorrected geometric/anatomical mismatch. The model's accuracy supports radiotherapy planning in pediatric brain tumors through risk-structure delineation and target-volume segmentation in GCTs.